© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4552
    Prev
    Next
    INDEX
    Explanations

    medical conditions related to respiratory issues, particularly sinusitis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Nasal congestion, nasal passages, or related nasal symptoms

    np_acts-logits-general · gemini-2.0-flash

    nasal congestion and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.97
    期刊论文
    -0.72
    AddTagHelper
    -0.66
    tagHelperRunner
    -0.64
     Zel
    -0.64
    ⓘ
    -0.62
    Geplaatst
    -0.61
    modelBuilder
    -0.60
    IVEREF
    -0.60
    contentLoaded
    -0.59
    POSITIVE LOGITS
     nose
    1.24
     nasal
    1.14
     Nose
    1.04
     noses
    1.04
    Nose
    0.99
     nostrils
    0.98
     Nasal
    0.97
    nose
    0.94
     nariz
    0.93
     nost
    0.89
    Activations Density 0.431%

    No Known Activations